In the last decade, with the increasing availability of digital video material, advanced applications based on storage and transmission of video data (digital libraries, video communication over the networks, digital TV, video-on-demand, etc.) began to appear. Their full utilization depends on the capability of information providers to organize and structure video data, as well as on the possibility of intermediate and final users to access the information.
From this point of view, automatic video temporal segmentation is a necessary task. As we showed in this chapter, much work has been done to individuate algorithms and methods in this area, but results are often too much depending on the peculiarity of input data. Research effort is still necessary to find generally effective and computationally manageable solutions to the problem.